%matplotlib inline

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib import cm

import ipyparallel as ipp

from time import time
from datetime import datetime

import motif as mf

from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
from sklearn.decomposition import PCA
from sklearn.utils import shuffle
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import roc_curve, roc_auc_score
from sklearn.model_selection import train_test_split, cross_val_score, cross_validate

from scipy.stats import spearmanr
from scipy.stats import pearsonr

Intel(R) Extension for Scikit-learn* enabled (https://github.com/intel/scikit-learn-intelex)

### set parameters for the motif analysis

PROTEIN_NAME = 'RBM24'
PROT_CONC = 0.002  # free protein concentration at binding reation; PBM typically 0.1 and RNACompete typically 0.002
BOTH_STRANDS = False  # wheter both strands are present for binding; True if double-stranded DNA or RNA is used as probes

STAGES=mf.stage(protein=PROTEIN_NAME)

### read data

## RNAcompete sample data
#dfprobes_raw=pd.read_excel('./data/RNAcompete/A2BP1.xlsx')
#dfprobes_raw=pd.read_excel('./data/RNAcompete/HNRNPA1.xlsx')
#dfprobes_raw=pd.read_excel('./data/RNAcompete/PTBP1.xlsx')
dfprobes_raw=pd.read_excel('./data/RNAcompete/RBM24.xlsx')


#dfprobes_raw=pd.read_csv('./data/samplePBMs/Mlx__pTH2882_HK.raw', sep='\t')
#dfprobes_raw=pd.read_csv('./data/samplePBMs/Klf9__pTH2353_HK.raw', sep='\t')
#dfprobes_raw=pd.read_csv('./data/samplePBMs/Prdm11__pTH3455_HK.raw', sep='\t')
#dfprobes_raw=pd.read_csv('./data/samplePBMs/Sox10__pTH1729_HK.raw', sep='\t')


print('Columns of imported Data File: %s' % dfprobes_raw.columns)
#dfprobes_raw.describe()
#dfprobes_raw.info()

Columns of imported Data File: Index(['Probe_Set', 'RNA_Seq', 'Probe_ID', 'norm', 'raw'], dtype='object')

### select columns for probe sequence and signal

column_sequence = 'RNA_Seq'
column_signal = 'norm'
#background_signal = 'mean_background_intensity'  #set to None if not needed
background_signal=None

#basic preprocessing
dfprobes_raw[column_signal] = dfprobes_raw[column_signal].apply(
    lambda a: np.NaN if a == ' ' else a)
dfprobes_raw[column_signal] = dfprobes_raw[column_signal].apply(
    lambda a: np.NaN if a == '' else a)
dfprobes_raw[column_sequence] = dfprobes_raw[column_sequence].apply(
    lambda a: np.NaN if str(a).lower() == 'nan' else a)
dfprobes_raw[column_sequence] = dfprobes_raw[column_sequence].apply(
    lambda a: np.NaN if a == '' else a)
dfprobes_raw = dfprobes_raw.dropna()

#construct new dataframe with only necessary data
if type(background_signal) == type(None):
    dfprobes = pd.DataFrame({
        'seq':
        dfprobes_raw[column_sequence].astype(str),
        'signal binding':
        dfprobes_raw[column_signal].astype(np.float32)
    })  #rebuild dataframe
else:
    dfprobes = pd.DataFrame({
        'seq':
        dfprobes_raw[column_sequence].astype(str),
        'signal':
        dfprobes_raw[column_signal].astype(np.float32),
        'background':
        dfprobes_raw[background_signal].astype(np.float32)
    })  #rebuild dataframe
    dfprobes['signal binding'] = dfprobes['signal'] - dfprobes['background']

dfprobes = dfprobes.dropna()    

    
# display main properties of data set
dfprobes['signal binding'].plot(figsize=(15, 5))
dfprobes.describe()

### check type of nucleic acid

dfprobes['seq'] = dfprobes['seq'].apply(
    lambda seq: seq.upper().replace(" ", ""))  #upper and remove blanks
dfprobes['RNA'] = dfprobes['seq'].apply(
    lambda seq: all(char in 'ACGU' for char in seq))
dfprobes['DNA'] = dfprobes['seq'].apply(
    lambda seq: all(char in 'ACGT' for char in seq))
non_RNA_counts = len(dfprobes[dfprobes['RNA'] == False])
non_DNA_counts = len(dfprobes[dfprobes['DNA'] == False])

if non_RNA_counts < non_DNA_counts:
    NUC_TYPE = 'RNA'
    print('I: RNA probes detected!')
else:
    NUC_TYPE = 'DNA'
    print('I: DNA probes detected!')

if NUC_TYPE == 'RNA' and non_RNA_counts != 0:
    print(
        'E: The probe sequences appear to be RNA, however there are some non-RNA nucleotides in the sequences.'
    )
    print('E: Please check the following sequnces %s' %
          dfprobes[dfprobes['RNA'] == False])

if NUC_TYPE == 'DNA' and non_DNA_counts != 0:
    print(
        'E: The probe sequences appear to be RNA, however there are some non-RNA nucleotides in the sequences.'
    )
    print('E: Please check the following sequnces %s' %
          dfprobes[dfprobes['DNA'] == False])

I: RNA probes detected!

### option to add a constant sequence at the 3' end and 5' end
sequence_to_be_added_5 = ''
sequence_to_be_added_3 = ''  # standard PBM arrays: CCTGTGTGAAATTGTTATCCGCTCT T7 array: GTCTTGA..
dfprobes['seq'] = sequence_to_be_added_5.upper(
) + dfprobes['seq'] + sequence_to_be_added_3.upper()
print(
    f"I: The nucleotide sequence {sequence_to_be_added_5.upper()} has been added to the 5' end all probe sequences."
)
print(
    f"I: The nucleotide sequence {sequence_to_be_added_3.upper()} has been added to the 3' end all probe sequences."
)

I: The nucleotide sequence  has been added to the 5' end all probe sequences.
I: The nucleotide sequence  has been added to the 3' end all probe sequences.

### egalize length
dfprobes['seq_length'] = dfprobes['seq'].apply(len)

if max(dfprobes['seq_length']) != min(dfprobes['seq_length']):
    print('I: Probes length is not uniform, detected range: %i ..%i' %
          (min(dfprobes['seq_length']), max(dfprobes['seq_length'])))
    max_length = max(dfprobes['seq_length'])
    dfprobes['padded_sequence'] = dfprobes['seq'].apply(
        lambda seq: seq + ((max_length - len(seq)) * '-'))
    print(
        "I: Probe sequences have been padded at the 5' to the uniform length of %i nucleotides"
        % max_length)
else:
    print('I: Probe sequences have the uniform length of %i nucleotides' %
          (dfprobes['seq_length'].median()))
    dfprobes['padded_sequence'] = dfprobes['seq']

print('I: Total datasets contains %i sequences.' % len(dfprobes))

# visualize composition of each position
df_nucleotides = mf.split_sequence_in_nucleotides(dfprobes['padded_sequence'])
dfcount = pd.DataFrame(index=['A', 'C', 'G', 'T', 'U', '-'])
for column in df_nucleotides:
    dfcount[column] = df_nucleotides[column].value_counts()
dfcount = dfcount.fillna(0)  #zeros for NaN
dfcount.transpose().plot(figsize=(15, 5), kind='bar')
print('I: Visualisation of the base composition per position')
print(
    'I: If positions are invariant they can be removed before sequence analysis.'
)

I: Probes length is not uniform, detected range: 30 ..41
I: Probe sequences have been padded at the 5' to the uniform length of 41 nucleotides
I: Total datasets contains 240076 sequences.
I: Visualisation of the base composition per position
I: If positions are invariant they can be removed before sequence analysis.

# You may remove invariant continuos positions by adjusting the slicing.
# It is recommended to leave a few invariant positions to allow for binding events
# between the variable and constant part of the probes.

dfprobes['padded_sequence'] = dfprobes['padded_sequence'].apply(lambda s: s[:38])  ### <==== do the slicing here

# visualize composition of each position
print('I: Visualisation of the base composition per position after slicing.')
df_nucleotides = mf.split_sequence_in_nucleotides(dfprobes['padded_sequence'])
dfcount = pd.DataFrame(index=['A', 'C', 'G', 'T', 'U', '-'])
for column in df_nucleotides:
    dfcount[column] = df_nucleotides[column].value_counts()
dfcount = dfcount.fillna(0)  #zeros for NaN
dfcount.transpose().plot(figsize=(15, 5), kind='bar')
plt.show()

# preparation for later classification
mean = dfprobes['signal binding'].mean()
std = dfprobes['signal binding'].std()
THRESHOLD = mean + 4 * std  #4*std used according to Weirauch et al., 2013
dfprobes['positive probe'] = dfprobes['signal binding'].apply(
    lambda s: True if s > THRESHOLD else False)

print(
    'I: The whole dataset has been used to set the threshold for a positive probe.'
)
print('I: The threshold is %f' % THRESHOLD)
print(
    f"I: {len(dfprobes[dfprobes['positive probe']])} probes of {len(dfprobes)} are above threshold."
)

if len(dfprobes[dfprobes['positive probe']]) == 0:
    print(
        'E: No probe above THRESHOLD. Classification is not possible. Please adjust the THRESHOLD.'
    )

I: Visualisation of the base composition per position after slicing.

I: The whole dataset has been used to set the threshold for a positive probe.
I: The threshold is 11.679949
I: 2739 probes of 240076 are above threshold.

### Shuffle and prepare dataset for training and testing

# shuffle and split
dfprobes = shuffle(dfprobes)
dftrain, dftest = train_test_split(dfprobes, test_size=0.2)

print(
    'I: The whole dataset has been split in training (80%) and test (20%) datasets.'
)

# display histogramms of test and training set
dftrain['signal binding'].plot(kind='hist', bins=25).axvline(x=THRESHOLD, color='r', linestyle='-.', lw=0.5, label='threshold classification')
dftest['signal binding'].plot(kind='hist', bins=25)
plt.show()

# generate a subset with maximal 1000 probes

downsampled_size = 1000  # You may change downsampled size here.

percentile = 0.5 * downsampled_size / len(
    dftrain
) * 100  #percentile required for lowest and highest to achieve down-sampled size
if percentile < 4:
    percentile = 4  #do not use only the extreme values
elif percentile > 10:
    percentile = 10  #avoid taking value from the mid-range

if len(dftrain) * percentile * 2 / 100 < downsampled_size / 4:
    print('W: The subset only contains %i probes - a rather low number.' %
          dftrain * percentile * 2 / 100)

print(
    'I: A downsampled dataset containing the lowest and highest %.1f %% of the dataset is generated.'
    % percentile)
dfsubset_high = dftrain[dftrain['signal binding'] >= dftrain['signal binding'].quantile(1 - percentile / 100)]  # highest part
dfsubset_low = dftrain[dftrain['signal binding'] <= dftrain['signal binding'].quantile(percentile / 100)]  # lowest part
print('I: Median values of lowest and highest %.1f %%:  %r  %r' %
      (percentile, dfsubset_low['signal binding'].quantile(0.5),
       dfsubset_high['signal binding'].quantile(0.5)))

if len(dfsubset_high) + len(dfsubset_low) > downsampled_size:
    print('I: The dataset is further downsampled to %i sequences.' %
          downsampled_size)
    dfsubset_high = dfsubset_high.sample(downsampled_size - int(downsampled_size / 2))
    dfsubset_low = dfsubset_low.sample(int(downsampled_size / 2))
    dfsubset = pd.concat([dfsubset_high, dfsubset_low])
else:
    dfsubset = pd.concat([dfsubset_high, dfsubset_low])

dfsubset = shuffle(dfsubset)   
    
# display main properties of downsampled data set
print('I: Histogramm of the downsampled dataset along the with classification threshold.')
dfsubset['signal binding'].plot(kind='hist', bins=25).axvline(x=THRESHOLD, color='r', linestyle='-.', lw=0.5, label='threshold classification')
plt.show()

# establish numpy arrays of the sequenc and binding data in the dataframes

# complete data
X=mf.hotencode_sequence(dfprobes['padded_sequence'], nuc_type=NUC_TYPE)
y=np.array(dfprobes['signal binding'])

# training set
X_train=mf.hotencode_sequence(dftrain['padded_sequence'], nuc_type=NUC_TYPE)
y_train=np.array(dftrain['signal binding'])

# subset of training set
X_subset=mf.hotencode_sequence(dfsubset['padded_sequence'], nuc_type=NUC_TYPE)
y_subset=np.array(dfsubset['signal binding'])

# test set
X_test=mf.hotencode_sequence(dftest['padded_sequence'], nuc_type=NUC_TYPE)
y_test=np.array(dftest['signal binding'])

I: The whole dataset has been split in training (80%) and test (20%) datasets.

I: A downsampled dataset containing the lowest and highest 4.0 % of the dataset is generated.
I: Median values of lowest and highest 4.0 %:  -1.5133719444274902  8.587244033813477
I: The dataset is further downsampled to 1000 sequences.
I: Histogramm of the downsampled dataset along the with classification threshold.

### perform a quick & dirty round for a short motif by fitting on subset to check data integrity

#fit regression quick_model
quick_model=mf.findmotif(motif_length=3, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS, ftol=0.01)

start = time()
quick_model.fit(X_subset,y_subset)
print("I: Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
quick_model.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('quick', quick_model)
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Optimization took 0.01 hours.
I: energy matrix and logos:

        A      C      G      U
0   3248  15056 -11659  -6645
1   7213    294   2650 -10158
2  15984  -1385 -10494  -4105

I: summed absolute energies of each position:
0    36609
1    20317
2    31969
dtype: int64

I: averaged summed energy over all positions: 29632
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -21878 +/- 15426
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00112 .. 6.60340 (ratio: 5905.2)
I: number of probes: 1000
I: Pearson Correlation  r: 0.6400
I: mean absolute error: 3.9564

I: Classification performance AUROC: 0.8002

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo
0	quick	RBM24	1000	3	0.639962	0.800222	-21161.022239	False	5905.204214	6.603397	0.001118	3248,..	suppressed

#### Perfrom GridCV Search for exploration of the motif length goal: identify the minimum motif length which gives a good r-value

# optional: allow for global optimization to verify whether the local optimization is good enough
# not recommended include fitG0=True. This option should only be considered when the local optimization is started with an approximate motif and the start parameter is set
# not recommended set time_dissociation. The effect of dissociation should be only considered when the local optimization is started with an approximate motif.


# prepare grid search over motif_length
model_grid=mf.findmotif(protein_conc=PROT_CONC, both_strands=BOTH_STRANDS)
param_grid = {"motif_length": [3,4,5,6,7]}     # choose sensible range for length of motif

# define custom refit function
def custom_refit(cv_results):
    """returns index of max r2/sqrt(motif_length)"""
    df_grid=pd.DataFrame(cv_results)
    index=(df_grid['mean_test_score']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))).idxmax()
    return index

# run grid search and refit according to custom refit
grid_search = GridSearchCV(model_grid, param_grid=param_grid, verbose=2, cv=5, refit=custom_refit, n_jobs=-1)

start = time()
grid_search.fit(X_subset, y_subset)

print("I: GridSearchCV took %.2f hours for %d candidate parameter settings."
    % ((time() - start)/3600, len(grid_search.cv_results_["params"])))
print('I: number of samples: %i' %len(X_subset))

df_grid=pd.DataFrame(grid_search.cv_results_)
print('I: Plot of r2 vs motif length and vs root(motif length)')
df_grid.rename(columns={'mean_test_score':'r2'}, inplace=True)
df_grid.plot(kind='scatter', x='param_motif_length', y='r2', yerr='std_test_score', figsize=(5,3)).set_xticks(param_grid["motif_length"])
df_grid['r2/sqrt(length)']=df_grid['r2']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))
df_grid['std/sqrt(length)']=df_grid['std_test_score']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))
df_grid.plot(kind='scatter', x='param_motif_length', y='r2/sqrt(length)',yerr='std/sqrt(length)', figsize=(5,3)).set_xticks(param_grid["motif_length"])
plt.show()

best_index=df_grid['r2/sqrt(length)'].idxmax()
CORE_MOTIF_LENGTH=df_grid.loc[best_index, 'param_motif_length']
print(f'I: The maximum ({CORE_MOTIF_LENGTH}) is suggested as CORE_MOTIF_LENGTH')

print('I: motif obtained with the best estimator from gridCV search')
# print & display results from best estimator
model_grid=grid_search.best_estimator_
model_grid.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('best grid', model_grid)
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

Fitting 5 folds for each of 5 candidates, totalling 25 fits
I: GridSearchCV took 0.41 hours for 5 candidate parameter settings.
I: number of samples: 1000
I: Plot of r2 vs motif length and vs root(motif length)

I: The maximum (3) is suggested as CORE_MOTIF_LENGTH
I: motif obtained with the best estimator from gridCV search
I: energy matrix and logos:

        A      C      G      U
0  13465    863  -8751  -5577
1  -7065  12159   4945 -10038
2  10864   5875 -10142  -6597

I: summed absolute energies of each position:
0    28658
1    34208
2    33480
dtype: int64

I: averaged summed energy over all positions: 32116
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -21534 +/- 15644
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00243 .. 4.68339 (ratio: 1926.6)
I: number of probes: 1000
I: Pearson Correlation  r: 0.6723
I: mean absolute error: 3.7521

I: Classification performance AUROC: 0.8216

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo
0	quick	RBM24	1000	3	0.639962	0.800222	-21161.022239	False	5905.204214	6.603397	0.001118	3248,..	suppressed
1	best grid	RBM24	1000	3	0.672286	0.821637	-21161.022239	False	1926.602695	4.683390	0.002431	13465,..	suppressed

### run a number of identical optimizations with motif length found during grid search
### goal: find best motif through repetition, judge stabiltiy of optimization

#CORE_MOTIF_LENGTH=5  # adjust core motif length if needed, motif length can be changed later

# prepare for ipyparallel
number_of_optimizations = 20
model_list = [mf.findmotif(motif_length=CORE_MOTIF_LENGTH, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS)] * number_of_optimizations
X_list = [X_subset] * number_of_optimizations
y_list = [y_subset] * number_of_optimizations


def single_job(model, X, y):
    model.fit(X, y)
    return {'model':model}

# run the optimizations on ipp.cluster
start = time()
with ipp.Cluster(log_level=40) as rc:
    rc[:].use_pickle()
    view = rc.load_balanced_view()
    asyncresult = view.map_async(single_job, model_list, X_list, y_list)
    asyncresult.wait_interactive()
    result = asyncresult.get()
print("I: Optimization took %.2f hours." % ((time() - start) / 3600))


  
# assemble results and analyze
df_repetitions=pd.DataFrame(result)
df_repetitions['r (subset)']=df_repetitions['model'].apply(lambda e: e.rvalue)
df_repetitions['r (train)']=df_repetitions['model'].apply(lambda e: mf.linregress(e.predict(X_train),y_train).rvalue)
df_repetitions['r (test)']=df_repetitions['model'].apply(lambda e: mf.linregress(e.predict(X_test),y_test).rvalue)
df_repetitions['G0']=df_repetitions['model'].apply(lambda e: e.finalG0_)
df_repetitions['max binding']=df_repetitions['model'].apply(lambda e: e.max_binding_fit)
df_repetitions['min binding']=df_repetitions['model'].apply(lambda e: e.min_binding_fit)
df_repetitions['ratio'] = df_repetitions['model'].apply(lambda e: e.ratio)
df_repetitions['energies']=df_repetitions['model'].apply(lambda e: e.energies_)
#df_repetitions['information']=df_repetitions['model'].apply(lambda e: mf.energies2information(e.energies_))


# display results of the ensemble of optimizations
print('I: Results of the repeated motif finding, sorted according to the regression coefficient with the train dataset.')
df_repetitions.sort_values('r (train)', ascending=False, inplace=True)
mf.display_df(df_repetitions, nuc_type=NUC_TYPE)

  0%|          | 0/16 [00:00<?, ?engine/s]

single_job:   0%|          | 0/20 [00:00<?, ?tasks/s]

I: Optimization took 0.08 hours.
I: Results of the repeated motif finding, sorted according to the regression coefficient with the train dataset

	model	r (subset)	r (train)	r (test)	G0	max binding	min binding	ratio	energies	logo
9	suppressed	0.675089	0.431714	0.441789	-21161.022239	3.506545	0.004184	838.106345	-3107,..
1	suppressed	0.674710	0.431442	0.441110	-21161.022239	3.850769	0.000549	7013.355819	-1150,..
6	suppressed	0.675924	0.430932	0.440896	-21161.022239	0.607704	0.006739	90.171035	1061,..
4	suppressed	0.674862	0.429392	0.440788	-21161.022239	0.437828	0.000695	629.752961	-1109,..
5	suppressed	0.672470	0.425138	0.437443	-21161.022239	3.571959	0.021374	167.118935	13626,..
12	suppressed	0.648233	0.424618	0.436963	-21161.022239	0.815664	0.001272	641.311685	744,..
10	suppressed	0.647556	0.423815	0.436599	-21161.022239	2.416053	0.004035	598.798501	-3798,..
16	suppressed	0.649735	0.399202	0.410410	-21161.022239	6.952855	0.002558	2718.324442	-6840,..
15	suppressed	0.625676	0.390682	0.404531	-21161.022239	6.564163	0.003300	1989.353132	-5320,..
7	suppressed	0.622816	0.390456	0.404509	-21161.022239	6.160478	0.001997	3085.457618	-5188,..
8	suppressed	0.625977	0.390346	0.404607	-21161.022239	6.492934	0.004142	1567.625324	-5115,..
0	suppressed	0.624993	0.390083	0.404955	-21161.022239	6.534048	0.003173	2059.517488	-5848,..
19	suppressed	0.626848	0.388523	0.402295	-21161.022239	6.646463	0.011767	564.837999	-5751,..
3	suppressed	0.621042	0.387733	0.401384	-21161.022239	6.514459	0.007436	876.123935	-7638,..
2	suppressed	0.638667	0.387675	0.391630	-21161.022239	3.722502	0.208551	17.849352	-6038,..
11	suppressed	0.650352	0.382280	0.385559	-21161.022239	10.098513	0.299292	33.741378	-10138,..
17	suppressed	0.646588	0.376581	0.379799	-21161.022239	9.557511	0.048970	195.171486	-5490,..
14	suppressed	0.596959	0.368268	0.372088	-21161.022239	0.077441	0.002612	29.652772	15172,..
18	suppressed	0.594500	0.366020	0.369370	-21161.022239	2.976053	0.015070	197.476295	10579,..
13	suppressed	0.454399	0.254535	0.255676	-21161.022239	10.193789	0.011946	853.302628	4671,..

### compare energy matrices of ensemble using PCA
print('I: Histogram of the regression coefficients r obtained by repeated optimizaion with the subset.')
df_repetitions['r (subset)'].plot(kind='hist')
plt.show()

pca = PCA(n_components=2)
pca_2c=pca.fit_transform(df_repetitions['energies'].tolist())    
df_repetitions[['PCA1', 'PCA2']]=pca_2c
print('I: 2-dimensional PCA explained %i %% of variance.' %(sum(pca.explained_variance_ratio_)*100))
if sum(pca.explained_variance_ratio_)<0.5:
      print('W: 2-dimensional PCA explained only %i %% of variance' %(sum(pca.explained_variance_ratio_)*100))

print('I: Visualization of the PCA with the regression quality vs. subset and training dataset by color.')        
df_repetitions.plot(x='PCA1', y='PCA2', kind='scatter', c='r (subset)',cmap=cm.coolwarm, edgecolors='black', linewidths=0.3)
df_repetitions.plot(x='PCA1', y='PCA2', kind='scatter', c='r (train)',cmap=cm.coolwarm, edgecolors='black', linewidths=0.3)

I: Histogram of the regression coefficients r obtained by repeated optimizaion with the subset.

I: 2-dimensional PCA explained 63 % of variance.
I: Visualization of the PCA with the regression quality vs. subset and training dataset by color.

/home/GLipps/.local/lib/python3.8/site-packages/sklearn/utils/deprecation.py:101: FutureWarning: Attribute `n_features_` was deprecated in version 1.2 and will be removed in 1.4. Use `n_features_in_` instead.
  warnings.warn(msg, category=FutureWarning)

<matplotlib.axes._subplots.AxesSubplot at 0x7f4677e0e0d0>

# visualisation of the motif with the highest r with the train dataset
print('I: Best motif according to r (train) from the repeated optimizations.')
print('I: PCA components: %i, %i' %(df_repetitions.iloc[0]['PCA1'], df_repetitions.iloc[0]['PCA2']))
model_best_repetition=df_repetitions.iloc[0]['model']
model_best_repetition.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE) 
# store results and display stages
STAGES.append('best repetition', model_best_repetition, new_entries={'r (test)': mf.linregress(model_best_repetition.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Best motif according to r (train) from the repeated optimizations.
I: PCA components: 5668, -10706
I: energy matrix and logos:

       A      C      G     U
0 -3107  16524  -8068 -5349
1 -5277   9333   3997 -8053
2  2108  17482 -11328 -8262

I: summed absolute energies of each position:
0    33048
1    26661
2    39181
dtype: int64

I: averaged summed energy over all positions: 32963
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -22628 +/- 15991
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00418 .. 3.50655 (ratio: 838.1)
I: number of probes: 1000
I: Pearson Correlation  r: 0.6751
I: mean absolute error: 3.7272

I: Classification performance AUROC: 0.8227

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	RBM24	1000	3	0.639962	0.800222	-21161.022239	False	5905.204214	6.603397	0.001118	3248,..	suppressed		NaN
1	best grid	RBM24	1000	3	0.672286	0.821637	-21161.022239	False	1926.602695	4.683390	0.002431	13465,..	suppressed		NaN
2	best repetition	RBM24	1000	3	0.675089	0.822745	-21161.022239	False	838.106345	3.506545	0.004184	-3107,..	suppressed		0.441789

### motif finding on complete training dataset starting with best motif from repetitions

#fit & predict optimization starting with previous energy matrix
model_train=mf.findmotif(motif_length=CORE_MOTIF_LENGTH, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=model_best_repetition.energies_)
start = time()
model_train.fit(X_train,y_train)
print("I: Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
model_train.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('train dataset', model_train, new_entries={'r (test)': mf.linregress(model_train.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Optimization took 2.99 hours.
I: energy matrix and logos:

       A      C      G     U
0 -3362  16632  -7895 -5375
1 -4464   9488   3777 -8801
2  1453  17456 -11143 -7766

I: summed absolute energies of each position:
0    33264
1    26533
2    37820
dtype: int64

I: averaged summed energy over all positions: 32539
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -21662 +/- 15706
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00029 .. 3.82560 (ratio: 13135.3)
I: number of probes: 192060
I: Pearson Correlation  r: 0.4379
I: mean absolute error: 1.2832

I: Classification performance AUROC: 0.8986

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	RBM24	1000	3	0.639962	0.800222	-21161.022239	False	5905.204214	6.603397	0.001118	3248,..	suppressed		NaN
1	best grid	RBM24	1000	3	0.672286	0.821637	-21161.022239	False	1926.602695	4.683390	0.002431	13465,..	suppressed		NaN
2	best repetition	RBM24	1000	3	0.675089	0.822745	-21161.022239	False	838.106345	3.506545	0.004184	-3107,..	suppressed		0.441789
3	train dataset	RBM24	192060	3	0.437853	0.898590	-21161.022239	False	13135.304157	3.825597	0.000291	-3362,..	suppressed		0.448474

### Based on the motif of CORE_MOTIF_LENGTH analyze the neigbouring positions 
### whether their inclusion can improve the quality of the motif
df_positions=model_train.investigate_extension_parallel(X_train,y_train, end5=3, end3=3, nuc_type=NUC_TYPE)

list_positions=df_positions.index[df_positions['+2%']].tolist()+[0] # list of positions with an increase of2% and default position 0
ext5=-min(list_positions)
ext3=max(list_positions)
print("I: It is suggested to extend the core motif at the 5' end by %i and at the 3' end by %i positions." %(ext5, ext3))

  0%|          | 0/6 [00:00<?, ?engine/s]

job5:   0%|          | 0/3 [00:00<?, ?tasks/s]

job3:   0%|          | 0/3 [00:00<?, ?tasks/s]

I: Optimization took 1.08 hours.

I: It is suggested to extend the core motif at the 5' end by 2 and at the 3' end by 3 positions.

### fit & predict optimization starting with extended energy matrix if extension appears to improve prediction

if ext5+ext3!=0: #extension suggestion from previous analysis of the bordering positions
    expanded_energies=model_train.energies_
    # append energies of single-optimized bordering positions to energies of central part
    if ext5!=0:
        energies_5=np.concatenate(df_positions['energies'][(df_positions.index<0) & (df_positions.index>=-ext5)].to_numpy())
        expanded_energies=np.concatenate((energies_5, expanded_energies))
    if ext3!=0:
        energies_3=np.concatenate(df_positions['energies'][(df_positions.index<=ext3) & (df_positions.index>0)].to_numpy().flatten())
        expanded_energies=np.concatenate((expanded_energies,  energies_3))

    print('I: Optimization started with following extended motif.')
    mf.energies2logo(expanded_energies, nuc_type=NUC_TYPE)
    expanded_motif_length=len(expanded_energies)//4
        
    model_extended=mf.findmotif(motif_length=expanded_motif_length, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=expanded_energies)

    start = time()
    model_extended.fit(X_train,y_train)
    print("Optimization took %.2f hours." % ((time() - start)/3600))

    # print & display main results
    model_extended.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

    # store results and display stages
    STAGES.append('train, extended', model_extended, new_entries={'r (test)': mf.linregress(model_extended.predict(X_test),y_test).rvalue})
    mf.display_df(STAGES.df, nuc_type=NUC_TYPE)
else:
    print('I: Motif is not extended based on previous analysis.')

I: Optimization started with following extended motif.
Optimization took 47.80 hours.
I: energy matrix and logos:

       A      C      G     U
0 -4696  17309  -7876 -4736
1 -1351   1371   1416 -1435
2 -3767  17430  -7656 -6006
3   838   5781    211 -6831
4  2085  17500 -10829 -8756
5  -601    659    -83    24
6  -624    722     64  -162
7  -300    499   -573   374

I: summed absolute energies of each position:
0    34619
1     5575
2    34861
3    13663
4    39171
5     1368
6     1573
7     1748
dtype: int64

I: averaged summed energy over all positions: 16572
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -7384 +/- 18470
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00000 .. 0.20078 (ratio: 7286188.2)
I: number of probes: 192060
I: Pearson Correlation  r: 0.5405
I: mean absolute error: 1.1852

I: Classification performance AUROC: 0.9437

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	RBM24	1000	3	0.639962	0.800222	-21161.022239	False	5.905204e+03	6.603397	1.118233e-03	3248,..	suppressed		NaN
1	best grid	RBM24	1000	3	0.672286	0.821637	-21161.022239	False	1.926603e+03	4.683390	2.430906e-03	13465,..	suppressed		NaN
2	best repetition	RBM24	1000	3	0.675089	0.822745	-21161.022239	False	8.381063e+02	3.506545	4.183891e-03	-3107,..	suppressed		0.441789
3	train dataset	RBM24	192060	3	0.437853	0.898590	-21161.022239	False	1.313530e+04	3.825597	2.912454e-04	-3362,..	suppressed		0.448474
4	train, extended	RBM24	192060	8	0.540482	0.943699	-6602.179517	False	7.286188e+06	0.200779	2.755608e-08	-4696,..	suppressed		0.542701

### fit & predict optimization starting with extended energy matrix plus one bordering position on each side if current bordering position exceed the information of 0.25

last_model=STAGES.df.at[max(STAGES.df.index),'model']   
I_5=mf.energies2information(last_model.energies_[0:4])>=0.25 #sufficient information content of 5' end position
I_3=mf.energies2information(last_model.energies_[-4:])>=0.25 #sufficient information content of 3' end position

if I_5 or I_3:
    print('I: At least one of the bordering positions of the current motif has an information content of at least 0.25. Extending.')
    expanded_energies_with_border=mf.modify_energies(last_model.energies_, end5=I_5, end3=I_3)  
    mf.energies2logo(expanded_energies_with_border, nuc_type=NUC_TYPE)
    motif_length_with_border=len(expanded_energies_with_border)//4

    model_with_border=mf.findmotif(motif_length=motif_length_with_border, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=expanded_energies_with_border)


    start = time()
    model_with_border.fit(X_train,y_train)
    print("Optimization took %.2f hours." % ((time() - start)/3600))

    # print & display main results
    model_with_border.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

    # store results and display stages
    STAGES.append('train, expanded, border', model_with_border, new_entries={'r (test)': mf.linregress(model_with_border.predict(X_test),y_test).rvalue})
    mf.display_df(STAGES.df, nuc_type=NUC_TYPE)
else:
    print('I: Both bordering positions of the found motif have an information content below 0.25. No futher optimization required.')

I: At least one of the bordering positions of the current motif has an information content of at least 0.25. Extending.

Optimization took 15.07 hours.
I: energy matrix and logos:

       A      C      G     U
0  -900    970    177  -246
1 -4477  17123  -7907 -4737
2 -1130   1121   1442 -1433
3 -3650  17357  -7670 -6035
4  1565   4667    139 -6371
5  2124  17500 -10812 -8812
6  -610    631   -149   128
7  -667    667    170  -170
8  -326    553   -547   320

I: summed absolute energies of each position:
0     2295
1    34246
2     5129
3    34715
4    12743
5    39249
6     1520
7     1675
8     1748
dtype: int64

I: averaged summed energy over all positions: 14813
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -4887 +/- 18431
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00000 .. 0.07550 (ratio: 7799556.3)
I: number of probes: 192060
I: Pearson Correlation  r: 0.5525
I: mean absolute error: 1.1770

I: Classification performance AUROC: 0.9453

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	RBM24	1000	3	0.639962	0.800222	-21161.022239	False	5.905204e+03	6.603397	1.118233e-03	3248,..	suppressed		NaN
1	best grid	RBM24	1000	3	0.672286	0.821637	-21161.022239	False	1.926603e+03	4.683390	2.430906e-03	13465,..	suppressed		NaN
2	best repetition	RBM24	1000	3	0.675089	0.822745	-21161.022239	False	8.381063e+02	3.506545	4.183891e-03	-3107,..	suppressed		0.441789
3	train dataset	RBM24	192060	3	0.437853	0.898590	-21161.022239	False	1.313530e+04	3.825597	2.912454e-04	-3362,..	suppressed		0.448474
4	train, extended	RBM24	192060	8	0.540482	0.943699	-6602.179517	False	7.286188e+06	0.200779	2.755608e-08	-4696,..	suppressed		0.542701
5	train, expanded, border	RBM24	192060	9	0.552515	0.945338	-4323.853665	False	7.799556e+06	0.075500	9.680018e-09	-900,..	suppressed		0.553035

last_model=STAGES.df.at[max(STAGES.df.index),'model']  
df_relevant_positions=last_model.explore_positions(X_train, y_train)
list_positions=df_relevant_positions.index[df_relevant_positions['-2%']].tolist() # list of positions with an increase of2% and default position 0
start_relevant=min(list_positions)
end_relevant=max(list_positions)
red5=-start_relevant
red3=end_relevant-len(df_relevant_positions)+1
print('I: The analysis suggests, that positions between %i to %i contribute significantly to the motif.' %(start_relevant, end_relevant))
last_model=STAGES.df.at[max(STAGES.df.index),'model']

if (end_relevant-start_relevant+1)in STAGES.df['motif length'].to_list():
    print('I: No need for a further optimization. An optimization with motif length of %i has already been done.' %(end_relevant-start_relevant))
    print('I: Checking whether G0 has been chosen correctly.')
    last_model.investigate_G0(X_train, y_train)
else:
    print('I: Bordering positions only marginally contributing towards regression quality are dropped.')
    print('I: New start energy for motif optimization:')
    start_final_model=mf.modify_energies(last_model.energies_, end5=red5, end3=red3)
    mf.energies2logo(start_final_model, nuc_type=NUC_TYPE)
    final_model=mf.findmotif(motif_length=len(start_final_model)//4, protein_conc=PROT_CONC, 
                             both_strands=BOTH_STRANDS, start=start_final_model)

    start = time()
    final_model.fit(X_train,y_train)
    print("Optimization took %.2f hours." % ((time() - start)/3600))

    # print & display main results
    final_model.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)
    
    print('I: Checking whether G0 has been chosen correctly.')
    final_model.investigate_G0(X_train, y_train)

    # store results and display stages
    STAGES.append('train, shrinked', final_model, new_entries={'r (test)': mf.linregress(final_model.predict(X_test),y_test).rvalue})
    mf.display_df(STAGES.df, nuc_type=NUC_TYPE)  

I: The analysis suggests, that positions between 0 to 5 contribute significantly to the motif
I: Bordering positions only marginally contributing towards regression quality are dropped.
I: New start energy for motif optimization:

Optimization took 9.51 hours.
I: energy matrix and logos:

       A      C      G     U
0  -926   1129     34  -237
1 -4428  16850  -7872 -4549
2 -1178   1227   1478 -1527
3 -3655  17253  -7663 -5934
4  1021   4316    176 -5514
5  1923  17501 -10759 -8665

I: summed absolute energies of each position:
0     2327
1    33700
2     5412
3    34507
4    11029
5    38849
dtype: int64

I: averaged summed energy over all positions: 20971
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -12144 +/- 17963
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00000 .. 0.81361 (ratio: 3111519.8)
I: number of probes: 192060
I: Pearson Correlation  r: 0.5264
I: mean absolute error: 1.1966

I: Classification performance AUROC: 0.9386
I: Checking whether G0 has been chosen correctly.
I: Current G0 = -11634 J/mol (see red broken line in figure below) with r = 0.526.
I: Maximal r is 0.526 at G0=-10634 J/mol (see green broken line below).
I: Maximal occupancy of 2 is reached at G0=-14634 J/mol (see blue broken line below).
I: Maximal occupancy of 0.2 is reached at G0=-7634 J/mol (see blue broken line below).

I: G0 is in a range leading to maximal probe occupancy between 0.2 and 2. Good.
I: Maximal r is close to r achieved with current G0. Good.

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	RBM24	1000	3	0.639962	0.800222	-21161.022239	False	5.905204e+03	6.603397	1.118233e-03	3248,..	suppressed		NaN
1	best grid	RBM24	1000	3	0.672286	0.821637	-21161.022239	False	1.926603e+03	4.683390	2.430906e-03	13465,..	suppressed		NaN
2	best repetition	RBM24	1000	3	0.675089	0.822745	-21161.022239	False	8.381063e+02	3.506545	4.183891e-03	-3107,..	suppressed		0.441789
3	train dataset	RBM24	192060	3	0.437853	0.898590	-21161.022239	False	1.313530e+04	3.825597	2.912454e-04	-3362,..	suppressed		0.448474
4	train, extended	RBM24	192060	8	0.540482	0.943699	-6602.179517	False	7.286188e+06	0.200779	2.755608e-08	-4696,..	suppressed		0.542701
5	train, expanded, border	RBM24	192060	9	0.552515	0.945338	-4323.853665	False	7.799556e+06	0.075500	9.680018e-09	-900,..	suppressed		0.553035
6	train, shrinked	RBM24	192060	6	0.526367	0.938642	-11634.110305	False	3.111520e+06	0.813613	2.614842e-07	-926,..	suppressed		0.524031

### optional adjustment of GO

G0=-29000   # <==== adjust G0 manually here

last_model=STAGES.df.at[max(STAGES.df.index),'model']
last_model.G0=G0

start = time()
last_model.fit(X_train,y_train)
print("Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
last_model.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('manually adjusted G0', model_with_border, new_entries={'r (test)': mf.linregress(last_model.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

STAGES.df.to_json('%s_%s-%s-%s_%s-%s.json' %(PROTEIN_NAME, datetime.now().year, datetime.now().month,datetime.now().day , datetime.now().hour, datetime.now().minute))
STAGES.df.to_pickle('%s_%s-%s-%s_%s-%s.pkl' %(PROTEIN_NAME, datetime.now().year, datetime.now().month,datetime.now().day , datetime.now().hour, datetime.now().minute))

mf.energies2logo(mf.reverse_complement(STAGES.df.at[4, 'energies']), nuc_type=NUC_TYPE)

import importlib

importlib.reload(mf)